SAMBA: Safe Model-Based Active Reinforcement Learning

In this paper, we propose SAMBA, a novel framework for safe reinforcement learning that combines aspects from probabilistic modelling, information theory, and statistics. Our method builds upon PILCO to enable active exploration using novel(semi-)metrics for out-of-sample Gaussian process evaluation optimised through a multi-objective problem that supports conditional-value-at-risk constraints. We evaluate our algorithm on a variety of safe dynamical system benchmarks involving both low and high-dimensional state representations. Our results show orders of magnitude reductions in samples and violations compared to state-of-the-art methods. Lastly, we provide intuition as to the effectiveness of the framework by a detailed analysis of our active metrics and safety constraints.

READ FULL TEXT

page 8

page 17

page 18

page 19

research
04/16/2021

Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions

This paper studies the problem of developing an approximate dynamic prog...
research
09/10/2021

Data Generation Method for Learning a Low-dimensional Safe Region in Safe Reinforcement Learning

Safe reinforcement learning aims to learn a control policy while ensurin...
research
11/10/2021

Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention

Safety has become one of the main challenges of applying deep reinforcem...
research
10/19/2020

Learning a Low-dimensional Representation of a Safe Region for Safe Reinforcement Learning on Dynamical Systems

For safely applying reinforcement learning algorithms on high-dimensiona...
research
01/23/2021

Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art

Safe learning and optimization deals with learning and optimization prob...
research
09/30/2022

Safe Exploration Method for Reinforcement Learning under Existence of Disturbance

Recent rapid developments in reinforcement learning algorithms have been...

Please sign up or login with your details

Forgot password? Click here to reset